COCO_train2014_000000256028.jpg: No such file or directory
northeastsquare opened this issue · 2 comments
after many tries, mutipathnet begins to train( I use command
model=resnet resnet_path=./data/models/resnet/resnet-18.t7 ./scripts/train_coco.sh
),
but it can't find COCO_train2014_000000256028.jpg.
I download the
http://msvocds.blob.core.windows.net/coco2014/train2014.zip
http://msvocds.blob.core.windows.net/coco2014/val2014.zip
and extract to
~/datasets/mscoco/
I don't know why, can you help me?
Training epoch 1/3200
/home/sam/torch/install/bin/lua: .../sam/torch/install/share/lua/5.1/threads/threads.lua:183: [thread 1 callback] /home/sam/torch/install/share/lua/5.1/image/init.lua:347: /home/sam/datasets/mscoco/train2014/COCO_train2014_000000256028.jpg: No such file or directory
stack traceback:
[C]: in function 'error'
/home/sam/torch/install/share/lua/5.1/image/init.lua:347: in function </home/sam/torch/install/share/lua/5.1/image/init.lua:333>
(tail call): ?
./loaders/concatloader.lua:62: in function <./loaders/concatloader.lua:60>
(tail call): ?
./BatchProviderBase.lua:19: in function 'getImages'
./BatchProviderROI.lua:128: in function 'sample'
./data.lua:64: in function <./data.lua:63>
(tail call): ?
(tail call): ?
...lua/5.1/torchnet/dataset/paralleldatasetiterator.lua:108: in function <...lua/5.1/torchnet/dataset/paralleldatasetiterator.lua:107>
(tail call): ?
[C]: in function 'xpcall'
.../sam/torch/install/share/lua/5.1/threads/threads.lua:234: in function 'callback'
...me/sam/torch/install/share/lua/5.1/threads/queue.lua:65: in function <...me/sam/torch/install/share/lua/5.1/threads/queue.lua:41>
[C]: in function 'pcall'
...me/sam/torch/install/share/lua/5.1/threads/queue.lua:40: in function 'dojob'
[string " local Queue = require 'threads.queue'..."]:15: in main chunk
stack traceback:
[C]: in function 'error'
.../sam/torch/install/share/lua/5.1/threads/threads.lua:183: in function 'dojob'
...lua/5.1/torchnet/dataset/paralleldatasetiterator.lua:179: in function '(for generator)'
./engines/fboptimengine.lua:55: in function <./engines/fboptimengine.lua:35>
(tail call): ?
train.lua:364: in main chunk
[C]: in function 'dofile'
.../torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:145: in main chunk
[C]: ?
Sorry, I mistake the dataset.
If I use the plain lua not luajit, nDonkey can only be set to 1.